agentleFS
Sign inStart free
dRafaleDdRafaleD/cybersec-skills/skills/operations/lean-phish/SKILL.md

lean-phish

Skill2 starsChanged 56 days agoMITView on GitHub

Runs token-efficient defensive phishing and email triage for Cursor and Codex on messages the user already has. Summarizes headers, flags lookalike From/Reply-To mismatch, and hashes attachments without opening them. Use when the user asks to triage a suspicious email, .eml, phishing, BEC, or lookalike domain. Do not use to write lures, send phishing, spoof mail, or execute attachments.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If they pasted a mail into chat, write it to a temp .eml and peek that.

    line 26
  2. Very specific:

    Run peek. Read stdout only.

    line 41
  3. Distinctive:

    Do not write phishing copy, landing pages, or spoofing how-to.

    line 47
  4. Distinctive:

    Do not execute or unpack attachments.

    line 48
  5. Distinctive:

    Do not log into the sender's provider or "verify" credentials.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lean Phish

Defensive mail triage on files the user already saved. Headers, mismatch, hash. Never send mail. Never open attachments.

Let SKILL_ROOT be the folder that contains this SKILL.md. Prefer python3; on Windows use py -3.

python3 "$SKILL_ROOT/scripts/lean_phish.py" peek /path/to/message.eml
python3 "$SKILL_ROOT/scripts/lean_phish.py" trim --chars 2500 path/to/out.txt

If they pasted a mail into chat, write it to a temp .eml and peek that. Do not dump the full body.

Mode

Default lean.

ModeBudget
leanpeek; references/headers.md; ≤6 findings
standard+ extra messages; ≤10 findings
deepstill no attachment execute; ≤12 findings

Workflow

  1. Confirm the mail is theirs to review (inbox they own, or a sample they collected).
  2. Run peek. Read stdout only.
  3. Compare From vs Return-Path/Reply-To, auth results if present, attachment names/hashes.
  4. Recommend: quarantine, do not click, reset their passwords if they already did click ([REDACTED]).

Hard rules

  • Do not write phishing copy, landing pages, or spoofing how-to.
  • Do not execute or unpack attachments. Hash only.
  • Do not log into the sender's provider or "verify" credentials.
  • Cap body quotes at 12 lines. Prefer the script summary.

Report template

## Lean-phish (`<mode>`)

**From:** <display> | **Return-Path host:** <host> | **Auth:** <spf/dkim/dmarc or unknown>

| Sev | Signal | Note | Action |
|-----|--------|------|--------|
| HIGH | reply-to mismatch | one clause | quarantine; warn users |

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free